© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 3444
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate spatial locations or directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mith
    -0.08
    itz
    -0.07
    icens
    -0.07
     Hitch
    -0.06
    china
    -0.06
     surroundings
    -0.06
     mimo
    -0.06
     sklad
    -0.06
    ÑĨеÑģ
    -0.06
    iew
    -0.06
    POSITIVE LOGITS
    ç·Ĵ
    0.07
    -long
    0.07
    .getLong
    0.06
     chain
    0.06
    hort
    0.06
     dÃłi
    0.06
     Lines
    0.06
     line
    0.06
    -chain
    0.06
     Chain
    0.06
    Activations Density 0.020%

    No Known Activations